Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.5410. Min Act: -0.1700
Data Index: 7589749 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.5410. Min Act: -0.1700
Data Index: 3399697 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.4785. Min Act: -0.1700
Data Index: 8609736 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.5097. Min Act: -0.1700
Data Index: 7045583 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.4472. Min Act: -0.1700
Data Index: 1367109 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.4472. Min Act: -0.1700
Data Index: 1478679 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.4785. Min Act: -0.1700
Data Index: 4005696 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.3535. Min Act: -0.1700
Data Index: 90090 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.3847. Min Act: -0.1700
Data Index: 1478678 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.3535. Min Act: -0.1700
Data Index: 1723192 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.3535. Min Act: -0.1700
Data Index: 79228 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.3222. Min Act: -0.1700
Data Index: 359232 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.3222. Min Act: -0.1700
Data Index: 3758493 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.2597. Min Act: -0.1700
Data Index: 7761062 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.2285. Min Act: -0.1700
Data Index: 5585399 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.2285. Min Act: -0.1700
Data Index: 8020115 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.2285. Min Act: -0.1700
Data Index: 8291162 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.1972. Min Act: -0.1700
Data Index: 1734676 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.1972. Min Act: -0.1700
Data Index: 8527587 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5410. Min Range: -7.5410
Max Act: 7.1972. Min Act: -0.1700
Data Index: 4473976 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19